© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 28078
    Prev
    Next
    INDEX
    Explanations

    sentences that include punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    73
    +0.11
    0.6%
    498
    +0.11
    0.6%
    313
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.11
    0.00
    129
    +0.11
    0.00
    258
    +0.11
    0.00
    Negative Logits
    boarding
    -1.47
    printStackTrace
    -1.38
    SERVER
    -1.37
    ography
    -1.34
     Dios
    -1.30
    end
    -1.29
    patcher
    -1.29
    aciones
    -1.27
    uary
    -1.27
    cation
    -1.27
    POSITIVE LOGITS
       ↵
    2.07
    č↵
    2.07
    ↵
    2.07
    2.07
        ↵
    2.07
    2.07
    č↵
    2.07
    2.07
    ↵
    2.07
    ↵↵
    2.07
    Activations Density 0.000%

    No Known Activations